Search

This paper presents an efficient Bayesian classification system based on Gaussian process classifiers (GPC) for detecting premature ventricular contraction (PVC) beats in electrocardiographic (ECG) signals. GPC have the advantage over SVM classifiers in that the parameters of its kernel are automatically selected according to the Bayesian estimation procedure based on Laplace approximation. We also propose to feed the classifier with different representations of the ECG signals based on morphology, discrete wavelet transform, and S-transform. The latter representation has never been used for ECG signals before. The experimental results obtained on 48 records (i.e., 109887 heart beats) of the MIT-BIH arrhythmia database showed that for all feature representations adopted in this work, the proposed GP classifier combined with the S-transform and trained with only 600 beats from PVC and Non-PVC classes can provide an overall accuracy and a sensitivity above 96% on the whole 48 recordings.

The detection and classification of heart arrhythmias using Electrocardiogram signals (ECG) has been an active area of research in the literature. Usually, to assess the effectiveness of a proposed classification method, training and test data are extracted from the same ECG record. However, in real scenarios test data may come from different records. In this case, the classification results may be less accurate due to the statistical shift between these samples. In order to solve this issue, we investigate, in this paper, the capabilities of two domain adaption methods proposed recently in the literature of machine learning. The first is known as domain transfer SVM, whereas the second is the importance weighted kernel logistic regression method. To assess the effectiveness of both methods, the MIT-BIH arrhythmia database is used in the experiments.

This paper proposes an interactive change detection method in multitemporal remote sensing images. The user needs to input markers related to change and no-change classes in the Difference image. Then this information is used by a support vector machine classifier to generate a spectral-change map. Then two different solutions based on Markov Random Field or Level-Set methods are used to incorporate the spatial contextual information in the decision process. While the Markov Random Field method is region driven, the level-set method exploits both region and contour for performing the segmentation task. Experiments conducted on two real remote-sensing images confirm the promising capabilities of the proposed method.

In this paper, we face the problem of collecting training samples for regression problems under an active learning perspective. In particular, we propose various active learning strategies specifically developed for regression approaches based on Gaussian processes (GPs) and support vector machines (SVMs). For GP regression, the first two strategies are based on the idea of adding samples that are dissimilar from the current training samples in terms of covariance measure, while the third one uses a pool of regressors in order to select the samples with the greater disagreements between the different regressors. Finally, the last strategy exploits an intrinsic GP regression outcome to pick up the most difficult and hence interesting samples to label. For SVM regression, the method based on the pool of regressors and two additional strategies based on the selection of the samples distant from the current support vectors in the kernel-induced feature space are proposed. The experimental results obtained on simulated and real data sets show that the proposed strategies exhibit a good capability to select samples that are significant for the regression process, thus opening the way to the active learning approach for remote-sensing regression problems.

This paper present a novel ensemble method for clustering very high spatial resolution (VHR) images that is composed of four main steps. Firstly, because of the important role of the spatial component in VHR imagery, a set of morphological features are extracted from the original image using many openings and closings with increasing structural element sizes. Secondly, we construct the ensemble by running the k-means algorithm several times with different initializations. In order to increase the diversity, different subsets of features are randomly selected at each time. Third, an optimal relabeling of the ensemble with respect to a representative partition is made via a pairwise relabeling procedure. Finally, the relabeled maps are fused with a Markov Random Field (MRF) method. The Experimental results obtained on two real VHR images acquired by the sensors IKONOS-2 and GeoEye-1 over urban areas confirmed the promising capabilities of the proposed approach.

In this paper, lip and eye features are applied to classify the human emotion through a set of irregular and regular ellipse fitting equations using Genetic algorithm (GA). South East Asian face is considered in this study. All six universally accepted emotions and one neutral are considered for classifications. The method which is fastest in extracting lip features is adopted in this study. Observation of various emotions of the subject lead to an unique characteristic of lips and eye. GA is adopted to optimize irregular ellipse and regular ellipse characteristics of the lip and eye features in each emotion respectively. That is, the top portion of lip configuration is a part of one ellipse and the bottom of different ellipse. Two ellipse based fitness equations are proposed for the lip configuration and relevant parameters that define the emotion are listed. One ellipse based fitness function is proposed for eye. The GA method approach has achieved reasonably successful classification of emotion. While performing classification, optimized values can mess or overlap with other emotions range. In order to overcome the overlapping problem between the emotions and at the same time to improve the classification, a neural network (NN) approach is implemented. The GA-NN based process exhibits a range of 83% - 90% classification of the emotion from the optimized feature of top lip, bottom lip and eye.

In this paper, a new 2D shape multiscale triangle-area representation (MTAR) is proposed. This representation utilizes a simple geometric principle, the area of a triangle, in obtaining a robust and efficient shape representation. The use of the wavelet transform for decomposing the boundary of the shapes improves the efficiency and robustness of the representation. The MTAR is more robust to the affine transformation, less affected by noise, and more selective than similar methods, e.g., the curvature scale-space CSS. Two tests, using MPEG-7 CE-shape-1 database, show that MTAR achieves better performance than the CSS under affine transformation and in the general shape retrieval.

Proposed is a piecewise-uniform resampling technique for an ECG signal. Different waves of a heartbeat signal are resampled at different rates. The proposed method was tested on a large number of ECG signals with high and low sampling resolutions. It has been found that the piecewise-uniform resampling method helps to improve the morphology alignment in general. This improvement is significant (e.g. 206%) when the durations of different heartbeats vary largely. Improved morphology alignment of resampled heartbeats could be useful in many applications such as cardiovascular engineering and ECG-based biometrics.

Problem statement: To design, implement, and test an algorithm for solving the square jigsaw puzzle problem, which has many applications in image processing, pattern recognition, and computer vision such as restoration of archeological artifacts and image descrambling. Approach: The algorithm used the gray level profiles of border pixels for local matching of the puzzle pieces, which was performed using dynamic programming to facilitate non-rigid alignment of pixels of two gray level profiles. Unlike the classical best-first search, the algorithm simultaneously located the neighbors of a puzzle piece during the search using the well-known Hungarian procedure, which is an optimal assignment procedure. To improve the search for a global solution, every puzzle piece was considered as starting piece at various starting locations. Results: Experiments using four well-known images demonstrated the effectiveness of the proposed approach over the classical piece-by-piece matching approach. The performance evaluation was based on a new precision performance measure. For all four test images, the proposed algorithm achieved 100% precision rate for puzzles up to 8×8. Conclusion: The proposed search mechanism based on simultaneous allocation of puzzle pieces using the Hungarian procedure provided better performance than piece-by-piece used in classical methods.

A real-time algorithm to automatically detect human faces and irises from color images has been developed. A Haar cascade-based algorithm has been applied for simple and fast face detection. The face image is then converted into a gray-scale image. Three types of image processing techniques have been tested to study their effect on the performance of the iris detection algorithm. Then iris candidates are extracted from the valley of the face region. The iris candidates are paired up and the cost of each possible pairing is computed by a combination of mathematical models. The pairing with the lowest cost is considered to be a pair of irises. The algorithm has been tested by quality images from a Logitech camera and noisy images from a Voxx CCD camera. The proposed algorithm has achieved a success rate of 83.60% for iris detection in an open office environment.

Dynamic space warping (DSW) has emerged as a very effective tool for matching shapes. However, a central computational difficulty associated with DSW arises when a boundary's starting point (or rotation angle) is unknown. In this article, the HopDSW algorithm is proposed to speed up the starting point computation. Rather than performing an exhaustive search for the correct starting point as in classical approaches, the proposed algorithm operates in a coarse-to-fine manner. The coarse search is global and uses a hopping step to exclude points from the search. Then the search is refined in the neighborhood of the solution of the coarse search. A criterion that governs selecting the hopping step parameter is given, which reduces the number of starting point computations by an order. For shape representation, a triangle area signature (TAS) is computed from triangles formed by the boundary points. Experimental results on the MPEG-7 CE-1 database of 1400 shapes show that the proposed algorithm returns the solution to an exhaustive search with a high degree of accuracy and a considerable reduction in the number of computations.